mmf
mmf copied to clipboard
[ECCV 2022] FashionViL: Fashion-Focused V+L Representation Learning
Thank you guys for the amazing job and for releasing FashionViL model. I would like to use such a model in an image-to-text retrieval setting, but I am not capable...
## ❓ Questions and Help Hi, I've fine-tuned the model on composition and now I would want to run inference using the fine-tuned weights to test some example which I...
## ❓ Questions and Help Hi, I came across a cross number of errors and fixed some as follows: - to fix (AttributeError: module 'distutils' has no attribute 'version'), DO...
## ❓ Questions and Help I download images in Fashion200k dataset at [https://github.com/xthan/fashion-200k](url) and annotations from your proposed Google Drive. However, after randomly visualizing some examples, I find most of...
## 🚀 Feature Thanks for your excellent work! As mentioned in the paper, `we first train a discrete VAE as the image tokenizer on our collected fashion images with the...